readable AI benchmarks (simplified)
Alibaba
Qwen3 235B A22B 2507 Instruct
Qwen3 235B A22B 2507 Instruct has a Quality Score of 23.2, ranking 325th among 551 scored models. Per 1M tokens, pricing is $0.230 input and $0.920 output. It accepts text input, outputs text, and has a 256k token context window. Its Reliability Score is 28.0, ranking 331st among 553 scored models, below average (total average: 35.6).
Quality Score23.2coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability28.0
Cache Discountnot available
Model specification
- Reasoning
- non-reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 256k tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.230
- Output
- $0.920
- Cached Input
- not available
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 12.0
- Coding
- not available
- Agentic
- not available
- Omniscience
- -44.0
- Correct
- 18.7%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 81.5%
Correct 18.7%Incorrect 62.7%Partial / not attempted 18.6%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 11%
- GPQA Diamond
- 75%
- CritPt
- 0%
- AA-Omniscience
- 28%
- AA-LCR
- 34%
Similar models
- Qwen3 Max (Preview)AlibabaQuality Score 24.0Value Score 16.8
- Qwen3.6 35B A3B (Non-reasoning)AlibabaQuality Score 21.7Value Score not available
- Qwen3.5 35B A3B (Non-reasoning)AlibabaQuality Score 20.9Value Score not available
- Qwen3 Coder 30B A3B InstructAlibabaQuality Score 19.7Value Score not available
- Qwen3 VL 235B A22B InstructAlibabaQuality Score 19.5Value Score not available
- Qwen3 MaxAlibabaQuality Score 26.1Value Score not available